Skip to content

Commit a737bc3

Browse files
committed
Aligned mutation style with other datasets
1 parent 964f247 commit a737bc3

File tree

1 file changed

+3
-0
lines changed

1 file changed

+3
-0
lines changed

build/beatAML/GetBeatAML.py

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -424,6 +424,9 @@ def map_and_combine(df, data_type, entrez_map_file, improve_map_file, map_file=N
424424
mapped_df.rename(columns={"hgvsc": "mutation"}, inplace=True)
425425
mapped_df.rename(columns={"labId": "sample_id"}, inplace=True)
426426
mapped_df.rename(columns={"Entrez_Gene_Id": "entrez_id"}, inplace=True)
427+
428+
#remove (gene) information preceeding the colon - this formats it like other datasets.
429+
mapped_df["mutation"] = mapped_df["mutation"].astype(str).str.split(":", n=1).str[-1]
427430

428431
variant_mapping = {
429432
'frameshift_variant': 'Frameshift_Variant',

0 commit comments

Comments
 (0)